© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 124678
    Prev
    Next
    INDEX
    Explanations

    no high-rise resorts or elevators

    np_acts-logits-general · gemini-2.5-flash-lite

    return/then

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    cheese
    0.47
    network
    0.47
    secretary
    0.46
    wtf
    0.45
    neck
    0.44
    hammad
    0.44
     blunt
    0.43
     _{
    0.43
     himself
    0.43
    coins
    0.42
    POSITIVE LOGITS
     балко
    0.62
     недвижимости
    0.47
    HERS
    0.45
    лм
    0.45
    VELOP
    0.43
    Мы
    0.43
    USION
    0.43
    Holly
    0.43
    🆕
    0.42
    ई
    0.42
    Activations Density 0.001%

    No Known Activations